Mistral Medium 3.1 pricing, context and benchmark
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.
Everything that matters, in one table
Context, pricing, cache, modalities and tooling, from the model registry and Artificial Analysis.
| Model | Mistral Medium 3.1 |
| Model ID | mistralai/mistral-medium-3.1 |
| Provider | Mistral |
| Release date | 13 August 2025 |
| Status | Generally available |
| Input context | 131,072 tokens |
| Output context | 104,857 tokens |
| Official input pricing | $0.4 per 1M tokens |
| Official output pricing | $2 per 1M tokens |
| Cache read pricing | $0.04 per 1M tokens |
| Market input pricing | $0.4 per 1M (cheapest route) |
| Market output pricing | $2 per 1M (cheapest route) |
| Input modalities | text · image · file |
| Output modalities | text |
| Reasoning control | Not exposed |
| Tool support | Functions, tool choice, structured outputs |
| Tokenizer | Mistral |
| Provider routes | 2 endpoints |
| Artificial Analysis index | Not published |
| Speed | Not published |
| Knowledge cutoff | Not publicly stated |
Input and output support
| Modality | Input | Output | Billed at |
|---|---|---|---|
| Text | ✓ yes | ✓ yes | $0.4 in |
| Image | ✓ yes | no | $0.4 in |
| Audio | no | no | not supported |
| Video | no | no | not supported |
| File (PDF) | ✓ yes | no | $0.4 in |
What is Mistral Medium 3.1?
Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.
It balances...
Mistral Medium 3.1 carries a 131K token window, uses the Mistral tokenizer and is served by Mistral. On Hoodgen it sits in the General tier of the model menu next to its siblings, so you can switch mid conversation without losing the thread.
Release and what changed from the previous version
This is the only release of Mistral Medium 3.1 on OpenRouter, released 13 August 2025. The provider has not published a knowledge cutoff, so treat training data as recent but unconfirmed for very new events.
Features and capabilities
What can you do with Mistral Medium 3.1?
Prompt caching and how to cut the bill
Cached input bills at $0.04 per million instead of $0.4. Keep the system prompt and documents first and the changing question last, so every call hits the cache.
Mistral Medium 3.1 pricing
Official pricing
- $0.04 cached input
- 131K context
- text, image, file input
- 2 routes on OpenRouter
- What Hoodgen routes to first
- Same model, lower bill
Market pricing, every route
| Provider | Tier | Input | Output | Cache read | Uptime 24h |
|---|---|---|---|---|---|
| Mistral | standard | $0.4 | $2 | $0.04 | 100.0% |
| Mistral | standard | $0.44 | $2.2 | $0.044 | n/a |
API pricing and cost calculator
| Rate | Per call | Total | Credits |
|---|---|---|---|
| Cheapest route | $0.0067 | $3.34 | 3174 |
| List price | $0.0067 | $3.34 | 3174 |
API and developer information
| Model ID | mistralai/mistral-medium-3.1 |
| Endpoint | https://openrouter.ai/api/v1/chat/completions |
| Parameters | frequency_penalty · max_tokens · presence_penalty · response_format · seed · stop · structured_outputs · temperature · tool_choice · tools · top_p |
| Streaming | Yes, server sent events |
| Modality string | text+image+file->text |
| Max prompt tokens | 131,072 |
| Max completion tokens | 104,857 |
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "mistralai/mistral-medium-3.1",
"messages": [{ "role": "user", "content": "Summarise this document." }],
"max_tokens": 1024
}'Model limitations
| Text only output | It cannot generate images, audio or video. Pair it with an image model on Hoodgen when you need visuals. |
| Output cap | 104,857 tokens per request. Long deliverables have to be chunked. |
| Benchmarks not published | Artificial Analysis does not publish an Intelligence Index for this release, so no benchmark score is claimed here. |
| Knowledge cutoff | The provider does not state a fixed cutoff for every release. Verify very recent events against search. |
Mistral Medium 3.1 vs other Mistral models
| Model | Context | Input /1M | Output /1M | AA index | Released |
|---|---|---|---|---|---|
| Mistral Medium 3.1 | 131K | $0.4 | $2 | n/a | 2025 |
| Mistral Large 3 2512 | 262K | $0.5 | $1.5 | n/a | 2025 |
| Devstral 2 2512 | 262K | $0.4 | $2 | n/a | 2025 |
| Ministral 3 8B 2512 | 262K | $0.15 | $0.15 | n/a | 2025 |
Privacy and data policy
- On Hoodgen, prompts and attachments answer that request and stay in your conversation history so you can reopen it. They are not used to train models.
- Requests route through OpenRouter to Mistral and are covered by that provider's API terms.
- Do not paste secrets or personal data you would not send to any hosted model.
Mistral Medium 3.1 questions, answered
Start chatting with Mistral Medium 3.1
Free to try on Hoodgen AI, with a live credit estimate before every send. No API key, no setup.